© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 20360
    Prev
    Next
    INDEX
    Explanations

    actions or scenarios that result in a negative consequence

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating an action or effect that leads to a consequence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Objective
    -0.71
    soType
    -0.71
    quickShipAvailable
    -0.69
    IRD
    -0.68
    details
    -0.68
    cedented
    -0.67
    orses
    -0.66
     Recomm
    -0.66
     resear
    -0.65
     attribution
    -0.65
    POSITIVE LOGITS
     explode
    1.49
     disinteg
    1.40
     crumble
    1.34
     vibr
    1.34
     disappear
    1.31
     melt
    1.30
     decay
    1.28
     protr
    1.28
     vanish
    1.27
     corro
    1.24
    Activations Density 0.307%

    No Known Activations